Files
FabledCurator/backend/app/api/gpu.py
T
bvandeusen 4daa3f2790
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 17s
CI / backend-lint-and-test (push) Successful in 25s
CI / integration (push) Successful in 3m33s
feat(ml): operator model swap — GPU re-embed + embedder as a setting (#1190)
Make the SigLIP embedder an operator choice (drop-in to SigLIP 2:
google/siglip2-so400m-patch16-512 is a verified 1152-d model at 512px → no
schema change, better small-cue fidelity). A swap = set model + re-embed +
retrain, all operator-driven; the GPU agent does the re-embed so it's fast.

- settings: embedder_model_name is now a setting (migration 0065) alongside the
  existing embedder_model_version; both editable + validated (non-empty) in the
  ml admin API. The server embedder loads by HF name (AutoImageProcessor/Model,
  model-agnostic), preferring the pre-downloaded local dir for the default so
  existing deploys don't re-download; rebuilds on a name change.
- agent: new 'embed' job = whole-image SigLIP embedding (mean-pool video frames)
  under the lease-announced model → POST /jobs/submit_embedding writes
  image_record.siglip_embedding + siglip_model_version. The lease now announces
  the model FROM THE SETTING (not a constant).
- re-embed routing: enqueue_gpu_backfill('embed') selects unembedded + stale-
  version images; 'siglip' now re-embeds concept crops whose version != current
  (so a swap re-triggers crops, not just the never-embedded back-catalogue). The
  CPU ml-worker backfill no longer re-embeds on a version mismatch (it can't
  churn the library at 512px) — the GPU agent owns version re-embeds. Daily
  'embed' + 'siglip' beats self-heal.
- scoring: score_image only bags embeddings in the CURRENT model's space (whole-
  image gated by siglip_model_version, concept regions by embedding_version) so a
  mid-swap stale vector isn't scored by new-space heads; legacy NULL = current.
- UI: GpuAgentCard "Embedding model (advanced)" — edit name/version, Save, and
  "Re-embed library (GPU)" (queues embed + siglip); points at SigLIP 2.

Tests: lease announces model + submit_embedding round-trip; enqueue 'embed'
selects stale/unembedded; stale-version excluded from scoring; embedder model
settable + empty rejected; siglip gate updated to current-version concept.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
2026-06-30 10:24:30 -04:00

249 lines
9.6 KiB
Python

"""GPU-job API (#114): the HTTP surface the desktop agent pulls work from.
The agent stays HTTP-only — it leases jobs, fetches image pixels via the normal
FC image URLs, and submits embeddings/regions back, all over this API. Redis and
Postgres are never exposed. The agent endpoints are gated by a bearer token
(Authorization: Bearer <token>) stored in AppSetting; the admin endpoints
(token / backfill / status) ride the browser session like the rest of FC's
homelab admin.
"""
import secrets
from quart import Blueprint, jsonify, request
from sqlalchemy import func, select
from sqlalchemy.dialects.postgresql import insert as pg_insert
from ..extensions import get_session
from ..models import AppSetting, GpuJob, ImageRecord, MLSettings
from ..services.gallery_service import image_url
from ..services.ml.gpu_jobs import GpuJobService
from ..services.ml.regions import RegionService
gpu_bp = Blueprint("gpu", __name__, url_prefix="/api/gpu")
_TOKEN_KEY = "gpu_agent_token"
def _bearer() -> str | None:
h = request.headers.get("Authorization", "")
return h[7:].strip() if h.startswith("Bearer ") else None
async def _agent_authed(session) -> bool:
supplied = _bearer()
if not supplied:
return False
stored = (
await session.execute(
select(AppSetting.value).where(AppSetting.key == _TOKEN_KEY)
)
).scalar_one_or_none()
return stored is not None and secrets.compare_digest(supplied, stored)
# --- Admin (browser): token + backfill + status -------------------------
@gpu_bp.route("/token", methods=["GET"])
async def get_token():
async with get_session() as session:
tok = (
await session.execute(
select(AppSetting.value).where(AppSetting.key == _TOKEN_KEY)
)
).scalar_one_or_none()
return jsonify({"token": tok, "configured": tok is not None})
@gpu_bp.route("/token/rotate", methods=["POST"])
async def rotate_token():
token = secrets.token_urlsafe(32)
async with get_session() as session:
await session.execute(
pg_insert(AppSetting)
.values(key=_TOKEN_KEY, value=token)
.on_conflict_do_update(index_elements=["key"], set_={"value": token})
)
await session.commit()
return jsonify({"token": token})
@gpu_bp.route("/status", methods=["GET"])
async def status():
async with get_session() as session:
rows = (
await session.execute(
select(GpuJob.status, func.count()).group_by(GpuJob.status)
)
).all()
counts = dict(rows)
return jsonify({
"pending": counts.get("pending", 0),
"leased": counts.get("leased", 0),
"done": counts.get("done", 0),
"error": counts.get("error", 0),
})
@gpu_bp.route("/backfill", methods=["POST"])
async def backfill():
"""Enqueue a job for every image that doesn't already have one for `task`."""
body = await request.get_json(silent=True) or {}
task = str(body.get("task") or "ccip")
from ..tasks.ml import enqueue_gpu_backfill
r = enqueue_gpu_backfill.delay(task)
return jsonify({"celery_task_id": r.id, "task": task}), 202
# --- Agent (bearer token): lease / submit / heartbeat / fail ------------
@gpu_bp.route("/jobs/lease", methods=["POST"])
async def lease():
body = await request.get_json(silent=True) or {}
agent_id = str(body.get("agent_id") or "agent")
try:
batch = min(max(int(body.get("batch_size", 8)), 1), 64)
except (TypeError, ValueError):
batch = 8
async with get_session() as session:
if not await _agent_authed(session):
return jsonify({"error": "unauthorized"}), 401
jobs = await GpuJobService(session).lease(agent_id, batch_size=batch)
ml = (
await session.execute(select(MLSettings).where(MLSettings.id == 1))
).scalar_one()
# image rows for url/mime in one shot
ids = [j.image_record_id for j in jobs]
imgs = {
i.id: i for i in (
await session.execute(
select(ImageRecord).where(ImageRecord.id.in_(ids))
)
).scalars()
} if ids else {}
await session.commit()
out = []
for j in jobs:
img = imgs.get(j.image_record_id)
if img is None:
continue
out.append({
"job_id": j.id,
"image_id": j.image_record_id,
"task": j.task,
"mime": img.mime,
"image_url": image_url(img.path),
# For video/animated: the agent samples at this cadence.
"frame_interval_seconds": ml.video_frame_interval_seconds,
"max_frames": ml.video_max_frames,
# The embedding model the agent must use for concept crops + the
# whole-image 'embed' task, so its vectors land in the SAME space
# the heads trained in. Server-announced FROM THE SETTING → the
# agent stays model-agnostic; an operator swap is a setting + a
# re-embed, never an agent change.
"embed_model_name": ml.embedder_model_name,
"embed_version": ml.embedder_model_version,
})
return jsonify({"jobs": out})
@gpu_bp.route("/jobs/heartbeat", methods=["POST"])
async def heartbeat():
body = await request.get_json(silent=True) or {}
agent_id = str(body.get("agent_id") or "agent")
job_ids = [int(x) for x in (body.get("job_ids") or [])]
async with get_session() as session:
if not await _agent_authed(session):
return jsonify({"error": "unauthorized"}), 401
n = await GpuJobService(session).heartbeat(agent_id, job_ids)
await session.commit()
return jsonify({"extended": n})
@gpu_bp.route("/jobs/submit", methods=["POST"])
async def submit():
"""Store a job's regions + close it. regions: [{kind, bbox:[x,y,w,h],
frame_time?, score?, *_version?, ccip_embedding?, siglip_embedding?}].
replace_kinds defaults to the kinds present in the submitted regions."""
body = await request.get_json(silent=True) or {}
agent_id = str(body.get("agent_id") or "agent")
job_id = body.get("job_id")
regions = body.get("regions") or []
if job_id is None:
return jsonify({"error": "job_id required"}), 400
kinds = body.get("replace_kinds") or sorted({r["kind"] for r in regions})
async with get_session() as session:
if not await _agent_authed(session):
return jsonify({"error": "unauthorized"}), 401
job = await session.get(GpuJob, int(job_id))
if job is None or job.status != "leased" or job.lease_token != agent_id:
return jsonify({"error": "lease_invalid"}), 409
if kinds:
await RegionService(session).replace_regions(
job.image_record_id, kinds, regions
)
await GpuJobService(session).complete(agent_id, int(job_id))
await session.commit()
return jsonify({"ok": True, "stored": len(regions)})
@gpu_bp.route("/jobs/submit_embedding", methods=["POST"])
async def submit_embedding():
"""Store a whole-image SigLIP embedding (the 'embed' task) on image_record +
close the job. Body: {agent_id, job_id, embedding:[...], embedding_version}.
This is how the GPU agent re-embeds the library under a new model (#1190) —
much faster than the CPU ml-worker at higher resolutions."""
body = await request.get_json(silent=True) or {}
agent_id = str(body.get("agent_id") or "agent")
job_id = body.get("job_id")
embedding = body.get("embedding")
version = body.get("embedding_version")
if job_id is None or not embedding or not version:
return jsonify({"error": "job_id, embedding, embedding_version required"}), 400
async with get_session() as session:
if not await _agent_authed(session):
return jsonify({"error": "unauthorized"}), 401
job = await session.get(GpuJob, int(job_id))
if job is None or job.status != "leased" or job.lease_token != agent_id:
return jsonify({"error": "lease_invalid"}), 409
img = await session.get(ImageRecord, job.image_record_id)
if img is not None:
img.siglip_embedding = embedding
img.siglip_model_version = version
await GpuJobService(session).complete(agent_id, int(job_id))
await session.commit()
return jsonify({"ok": True})
@gpu_bp.route("/jobs/fail", methods=["POST"])
async def fail():
body = await request.get_json(silent=True) or {}
agent_id = str(body.get("agent_id") or "agent")
job_id = body.get("job_id")
if job_id is None:
return jsonify({"error": "job_id required"}), 400
async with get_session() as session:
if not await _agent_authed(session):
return jsonify({"error": "unauthorized"}), 401
ok = await GpuJobService(session).fail(
agent_id, int(job_id), str(body.get("error") or "")
)
await session.commit()
return jsonify({"ok": ok})
@gpu_bp.route("/jobs/release", methods=["POST"])
async def release():
"""Graceful stop: the agent hands its still-leased jobs back to pending so
they're picked up immediately instead of waiting out the lease."""
body = await request.get_json(silent=True) or {}
agent_id = str(body.get("agent_id") or "agent")
job_ids = [int(x) for x in (body.get("job_ids") or [])]
async with get_session() as session:
if not await _agent_authed(session):
return jsonify({"error": "unauthorized"}), 401
n = await GpuJobService(session).release(agent_id, job_ids)
await session.commit()
return jsonify({"released": n})